x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 52 insertions, 0 deletions

diff --git a/fs/btrfs/relocation.h b/fs/btrfs/relocation.h
new file mode 100644
index 000000000..bb7a86e7d
--- /dev/null
+++ b/fs/btrfs/relocation.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_RELOCATION_H
+#define BTRFS_RELOCATION_H
+
+#include <linux/types.h>
+
+struct extent_buffer;
+struct btrfs_fs_info;
+struct btrfs_root;
+struct btrfs_trans_handle;
+struct btrfs_ordered_extent;
+struct btrfs_pending_snapshot;
+
+static inline bool should_relocate_using_remap_tree(const struct btrfs_block_group *bg)
+{
+	if (!btrfs_fs_incompat(bg->fs_info, REMAP_TREE))
+		return false;
+
+	if (bg->flags & (BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA_REMAP))
+		return false;
+
+	return true;
+}
+
+int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start,
+			       bool verbose);
+int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root);
+int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
+int btrfs_recover_relocation(struct btrfs_fs_info *fs_info);
+int btrfs_reloc_clone_csums(struct btrfs_ordered_extent *ordered);
+int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root,
+			  const struct extent_buffer *buf,
+			  struct extent_buffer *cow);
+void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
+			      u64 *bytes_to_reserve);
+int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
+			      struct btrfs_pending_snapshot *pending);
+int btrfs_should_cancel_balance(const struct btrfs_fs_info *fs_info);
+struct btrfs_root *find_reloc_root(struct btrfs_fs_info *fs_info, u64 bytenr);
+bool btrfs_should_ignore_reloc_root(const struct btrfs_root *root);
+u64 btrfs_get_reloc_bg_bytenr(struct btrfs_fs_info *fs_info);
+int btrfs_translate_remap(struct btrfs_fs_info *fs_info, u64 *logical, u64 *length);
+int btrfs_remove_extent_from_remap_tree(struct btrfs_trans_handle *trans,
+					struct btrfs_path *path,
+					u64 bytenr, u64 num_bytes);
+int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
+				   struct btrfs_block_group *bg);
+
+#endif